x86.c

		if (msr >= MSR_IA32_MC0_CTL &&
		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
			u32 offset = msr - MSR_IA32_MC0_CTL;
			/* only 0 or all 1s can be written to IA32_MCi_CTL
			 * some Linux kernels though clear bit 10 in bank 4 to
			 * workaround a BIOS/GART TBL issue on AMD K8s, ignore
			 * this to avoid an uncatched #GP in the guest
			 */
			if ((offset & 0x3) == 0 &&
			    data != 0 && (data | (1 << 10)) != ~(u64)0)
				return -1;
			vcpu->arch.mce_banks[offset] = data;
			break;
		}
		return 1;
	}
	return 0;
}

static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
{
	struct kvm *kvm = vcpu->kvm;
	int lm = is_long_mode(vcpu);
	u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64
		: (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32;
	u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
		: kvm->arch.xen_hvm_config.blob_size_32;
	u32 page_num = data & ~PAGE_MASK;
	u64 page_addr = data & PAGE_MASK;
	u8 *page;
	int r;

	r = -E2BIG;
	if (page_num >= blob_size)
		goto out;
	r = -ENOMEM;
	page = kzalloc(PAGE_SIZE, GFP_KERNEL);
	if (!page)
		goto out;
	r = -EFAULT;
	if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE))
		goto out_free;
	if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
		goto out_free;
	r = 0;
out_free:
	kfree(page);
out:
	return r;
}

static bool kvm_hv_hypercall_enabled(struct kvm *kvm)
{
	return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE;
}

static bool kvm_hv_msr_partition_wide(u32 msr)
{
	bool r = false;
	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
	case HV_X64_MSR_HYPERCALL:
		r = true;
		break;
	}

	return r;
}

static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	struct kvm *kvm = vcpu->kvm;

	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
		kvm->arch.hv_guest_os_id = data;
		/* setting guest os id to zero disables hypercall page */
		if (!kvm->arch.hv_guest_os_id)
			kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE;
		break;
	case HV_X64_MSR_HYPERCALL: {
		u64 gfn;
		unsigned long addr;
		u8 instructions[4];

		/* if guest os id is not set hypercall should remain disabled */
		if (!kvm->arch.hv_guest_os_id)
			break;
		if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) {
			kvm->arch.hv_hypercall = data;
			break;
		}
		gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT;
		addr = gfn_to_hva(kvm, gfn);
		if (kvm_is_error_hva(addr))
			return 1;
		kvm_x86_ops->patch_hypercall(vcpu, instructions);
		((unsigned char *)instructions)[3] = 0xc3; /* ret */
		if (copy_to_user((void __user *)addr, instructions, 4))
			return 1;
		kvm->arch.hv_hypercall = data;
		break;
	}
	default:
		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
			  "data 0x%llx\n", msr, data);
		return 1;
	}
	return 0;
}

static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	switch (msr) {
	case HV_X64_MSR_APIC_ASSIST_PAGE: {
		unsigned long addr;

		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
			vcpu->arch.hv_vapic = data;
			break;
		}
		addr = gfn_to_hva(vcpu->kvm, data >>
				  HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT);
		if (kvm_is_error_hva(addr))
			return 1;
		if (clear_user((void __user *)addr, PAGE_SIZE))
			return 1;
		vcpu->arch.hv_vapic = data;
		break;
	}
	case HV_X64_MSR_EOI:
		return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data);
	case HV_X64_MSR_ICR:
		return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data);
	case HV_X64_MSR_TPR:
		return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data);
	default:
		pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x "
			  "data 0x%llx\n", msr, data);
		return 1;
	}

	return 0;
}

int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	switch (msr) {
	case MSR_EFER:
		return set_efer(vcpu, data);
	case MSR_K7_HWCR:
		data &= ~(u64)0x40;	/* ignore flush filter disable */
		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
		if (data != 0) {
			pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
				data);
			return 1;
		}
		break;
	case MSR_FAM10H_MMIO_CONF_BASE:
		if (data != 0) {
			pr_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: "
				"0x%llx\n", data);
			return 1;
		}
		break;
	case MSR_AMD64_NB_CFG:
		break;
	case MSR_IA32_DEBUGCTLMSR:
		if (!data) {
			/* We support the non-activated case already */
			break;
		} else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) {
			/* Values other than LBR and BTF are vendor-specific,
			   thus reserved and should throw a #GP */
			return 1;
		}
		pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
			__func__, data);
		break;
	case MSR_IA32_UCODE_REV:
	case MSR_IA32_UCODE_WRITE:
	case MSR_VM_HSAVE_PA:
	case MSR_AMD64_PATCH_LOADER:
		break;
	case 0x200 ... 0x2ff:
		return set_msr_mtrr(vcpu, msr, data);
	case MSR_IA32_APICBASE:
		kvm_set_apic_base(vcpu, data);
		break;
	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
		return kvm_x2apic_msr_write(vcpu, msr, data);
	case MSR_IA32_MISC_ENABLE:
		vcpu->arch.ia32_misc_enable_msr = data;
		break;
	case MSR_KVM_WALL_CLOCK:
		vcpu->kvm->arch.wall_clock = data;
		kvm_write_wall_clock(vcpu->kvm, data);
		break;
	case MSR_KVM_SYSTEM_TIME: {
		if (vcpu->arch.time_page) {
			kvm_release_page_dirty(vcpu->arch.time_page);
			vcpu->arch.time_page = NULL;
		}

		vcpu->arch.time = data;

		/* we verify if the enable bit is set... */
		if (!(data & 1))
			break;

		/* ...but clean it before doing the actual write */
		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);

		vcpu->arch.time_page =
				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);

		if (is_error_page(vcpu->arch.time_page)) {
			kvm_release_page_clean(vcpu->arch.time_page);
			vcpu->arch.time_page = NULL;
		}

		kvm_request_guest_time_update(vcpu);
		break;
	}
	case MSR_IA32_MCG_CTL:
	case MSR_IA32_MCG_STATUS:
	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
		return set_msr_mce(vcpu, msr, data);

	/* Performance counters are not protected by a CPUID bit,
	 * so we should check all of them in the generic path for the sake of
	 * cross vendor migration.
	 * Writing a zero into the event select MSRs disables them,
	 * which we perfectly emulate ;-). Any other value should be at least
	 * reported, some guests depend on them.
	 */
	case MSR_P6_EVNTSEL0:
	case MSR_P6_EVNTSEL1:
	case MSR_K7_EVNTSEL0:
	case MSR_K7_EVNTSEL1:
	case MSR_K7_EVNTSEL2:
	case MSR_K7_EVNTSEL3:
		if (data != 0)
			pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
				"0x%x data 0x%llx\n", msr, data);
		break;
	/* at least RHEL 4 unconditionally writes to the perfctr registers,
	 * so we ignore writes to make it happy.
	 */
	case MSR_P6_PERFCTR0:
	case MSR_P6_PERFCTR1:
	case MSR_K7_PERFCTR0:
	case MSR_K7_PERFCTR1:
	case MSR_K7_PERFCTR2:
	case MSR_K7_PERFCTR3:
		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
			"0x%x data 0x%llx\n", msr, data);
		break;
	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
		if (kvm_hv_msr_partition_wide(msr)) {
			int r;
			mutex_lock(&vcpu->kvm->lock);
			r = set_msr_hyperv_pw(vcpu, msr, data);
			mutex_unlock(&vcpu->kvm->lock);
			return r;
		} else
			return set_msr_hyperv(vcpu, msr, data);
		break;
	default:
		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
			return xen_hvm_config(vcpu, data);
		if (!ignore_msrs) {
			pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
				msr, data);
			return 1;
		} else {
			pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n",
				msr, data);
			break;
		}
	}
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_msr_common);


/*
 * Reads an msr value (of 'msr_index') into 'pdata'.
 * Returns 0 on success, non-0 otherwise.
 * Assumes vcpu_load() was already called.
 */
int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
{
	return kvm_x86_ops->get_msr(vcpu, msr_index, pdata);
}

static int get_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;

	if (!msr_mtrr_valid(msr))
		return 1;

	if (msr == MSR_MTRRdefType)
		*pdata = vcpu->arch.mtrr_state.def_type +
			 (vcpu->arch.mtrr_state.enabled << 10);
	else if (msr == MSR_MTRRfix64K_00000)
		*pdata = p[0];
	else if (msr == MSR_MTRRfix16K_80000 || msr == MSR_MTRRfix16K_A0000)
		*pdata = p[1 + msr - MSR_MTRRfix16K_80000];
	else if (msr >= MSR_MTRRfix4K_C0000 && msr <= MSR_MTRRfix4K_F8000)
		*pdata = p[3 + msr - MSR_MTRRfix4K_C0000];
	else if (msr == MSR_IA32_CR_PAT)
		*pdata = vcpu->arch.pat;
	else {	/* Variable MTRRs */
		int idx, is_mtrr_mask;
		u64 *pt;

		idx = (msr - 0x200) / 2;
		is_mtrr_mask = msr - 0x200 - 2 * idx;
		if (!is_mtrr_mask)
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].base_lo;
		else
			pt =
			  (u64 *)&vcpu->arch.mtrr_state.var_ranges[idx].mask_lo;
		*pdata = *pt;
	}

	return 0;
}

static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data;
	u64 mcg_cap = vcpu->arch.mcg_cap;
	unsigned bank_num = mcg_cap & 0xff;

	switch (msr) {
	case MSR_IA32_P5_MC_ADDR:
	case MSR_IA32_P5_MC_TYPE:
		data = 0;
		break;
	case MSR_IA32_MCG_CAP:
		data = vcpu->arch.mcg_cap;
		break;
	case MSR_IA32_MCG_CTL:
		if (!(mcg_cap & MCG_CTL_P))
			return 1;
		data = vcpu->arch.mcg_ctl;
		break;
	case MSR_IA32_MCG_STATUS:
		data = vcpu->arch.mcg_status;
		break;
	default:
		if (msr >= MSR_IA32_MC0_CTL &&
		    msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
			u32 offset = msr - MSR_IA32_MC0_CTL;
			data = vcpu->arch.mce_banks[offset];
			break;
		}
		return 1;
	}
	*pdata = data;
	return 0;
}

static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data = 0;
	struct kvm *kvm = vcpu->kvm;

	switch (msr) {
	case HV_X64_MSR_GUEST_OS_ID:
		data = kvm->arch.hv_guest_os_id;
		break;
	case HV_X64_MSR_HYPERCALL:
		data = kvm->arch.hv_hypercall;
		break;
	default:
		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
		return 1;
	}

	*pdata = data;
	return 0;
}

static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data = 0;

	switch (msr) {
	case HV_X64_MSR_VP_INDEX: {
		int r;
		struct kvm_vcpu *v;
		kvm_for_each_vcpu(r, v, vcpu->kvm)
			if (v == vcpu)
				data = r;
		break;
	}
	case HV_X64_MSR_EOI:
		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
	case HV_X64_MSR_ICR:
		return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
	case HV_X64_MSR_TPR:
		return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
	default:
		pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
		return 1;
	}
	*pdata = data;
	return 0;
}

int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
{
	u64 data;

	switch (msr) {
	case MSR_IA32_PLATFORM_ID:
	case MSR_IA32_UCODE_REV:
	case MSR_IA32_EBL_CR_POWERON:
	case MSR_IA32_DEBUGCTLMSR:
	case MSR_IA32_LASTBRANCHFROMIP:
	case MSR_IA32_LASTBRANCHTOIP:
	case MSR_IA32_LASTINTFROMIP:
	case MSR_IA32_LASTINTTOIP:
	case MSR_K8_SYSCFG:
	case MSR_K7_HWCR:
	case MSR_VM_HSAVE_PA:
	case MSR_P6_PERFCTR0:
	case MSR_P6_PERFCTR1:
	case MSR_P6_EVNTSEL0:
	case MSR_P6_EVNTSEL1:
	case MSR_K7_EVNTSEL0:
	case MSR_K7_PERFCTR0:
	case MSR_K8_INT_PENDING_MSG:
	case MSR_AMD64_NB_CFG:
	case MSR_FAM10H_MMIO_CONF_BASE:
		data = 0;
		break;
	case MSR_MTRRcap:
		data = 0x500 | KVM_NR_VAR_MTRR;
		break;
	case 0x200 ... 0x2ff:
		return get_msr_mtrr(vcpu, msr, pdata);
	case 0xcd: /* fsb frequency */
		data = 3;
		break;
	case MSR_IA32_APICBASE:
		data = kvm_get_apic_base(vcpu);
		break;
	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
		return kvm_x2apic_msr_read(vcpu, msr, pdata);
		break;
	case MSR_IA32_MISC_ENABLE:
		data = vcpu->arch.ia32_misc_enable_msr;
		break;
	case MSR_IA32_PERF_STATUS:
		/* TSC increment by tick */
		data = 1000ULL;
		/* CPU multiplier */
		data |= (((uint64_t)4ULL) << 40);
		break;
	case MSR_EFER:
		data = vcpu->arch.efer;
		break;
	case MSR_KVM_WALL_CLOCK:
		data = vcpu->kvm->arch.wall_clock;
		break;
	case MSR_KVM_SYSTEM_TIME:
		data = vcpu->arch.time;
		break;
	case MSR_IA32_P5_MC_ADDR:
	case MSR_IA32_P5_MC_TYPE:
	case MSR_IA32_MCG_CAP:
	case MSR_IA32_MCG_CTL:
	case MSR_IA32_MCG_STATUS:
	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
		return get_msr_mce(vcpu, msr, pdata);
	case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
		if (kvm_hv_msr_partition_wide(msr)) {
			int r;
			mutex_lock(&vcpu->kvm->lock);
			r = get_msr_hyperv_pw(vcpu, msr, pdata);
			mutex_unlock(&vcpu->kvm->lock);
			return r;
		} else
			return get_msr_hyperv(vcpu, msr, pdata);
		break;
	default:
		if (!ignore_msrs) {
			pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
			return 1;
		} else {
			pr_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr);
			data = 0;
		}
		break;
	}
	*pdata = data;
	return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_msr_common);

/*
 * Read or write a bunch of msrs. All parameters are kernel addresses.
 *
 * @return number of msrs set successfully.
 */
static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
		    struct kvm_msr_entry *entries,
		    int (*do_msr)(struct kvm_vcpu *vcpu,
				  unsigned index, u64 *data))
{
	int i, idx;

	vcpu_load(vcpu);

	idx = srcu_read_lock(&vcpu->kvm->srcu);
	for (i = 0; i < msrs->nmsrs; ++i)
		if (do_msr(vcpu, entries[i].index, &entries[i].data))
			break;
	srcu_read_unlock(&vcpu->kvm->srcu, idx);

	vcpu_put(vcpu);

	return i;
}

/*
 * Read or write a bunch of msrs. Parameters are user addresses.
 *
 * @return number of msrs set successfully.
 */
static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
		  int (*do_msr)(struct kvm_vcpu *vcpu,
				unsigned index, u64 *data),
		  int writeback)
{
	struct kvm_msrs msrs;
	struct kvm_msr_entry *entries;
	int r, n;
	unsigned size;

	r = -EFAULT;
	if (copy_from_user(&msrs, user_msrs, sizeof msrs))
		goto out;

	r = -E2BIG;
	if (msrs.nmsrs >= MAX_IO_MSRS)
		goto out;

	r = -ENOMEM;
	size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
	entries = vmalloc(size);
	if (!entries)
		goto out;

	r = -EFAULT;
	if (copy_from_user(entries, user_msrs->entries, size))
		goto out_free;

	r = n = __msr_io(vcpu, &msrs, entries, do_msr);
	if (r < 0)
		goto out_free;

	r = -EFAULT;
	if (writeback && copy_to_user(user_msrs->entries, entries, size))
		goto out_free;

	r = n;

out_free:
	vfree(entries);
out:
	return r;
}

int kvm_dev_ioctl_check_extension(long ext)
{
	int r;

	switch (ext) {
	case KVM_CAP_IRQCHIP:
	case KVM_CAP_HLT:
	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
	case KVM_CAP_SET_TSS_ADDR:
	case KVM_CAP_EXT_CPUID:
	case KVM_CAP_CLOCKSOURCE:
	case KVM_CAP_PIT:
	case KVM_CAP_NOP_IO_DELAY:
	case KVM_CAP_MP_STATE:
	case KVM_CAP_SYNC_MMU:
	case KVM_CAP_REINJECT_CONTROL:
	case KVM_CAP_IRQ_INJECT_STATUS:
	case KVM_CAP_ASSIGN_DEV_IRQ:
	case KVM_CAP_IRQFD:
	case KVM_CAP_IOEVENTFD:
	case KVM_CAP_PIT2:
	case KVM_CAP_PIT_STATE2:
	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
	case KVM_CAP_XEN_HVM:
	case KVM_CAP_ADJUST_CLOCK:
	case KVM_CAP_VCPU_EVENTS:
	case KVM_CAP_HYPERV:
	case KVM_CAP_HYPERV_VAPIC:
	case KVM_CAP_HYPERV_SPIN:
	case KVM_CAP_PCI_SEGMENT:
	case KVM_CAP_DEBUGREGS:
	case KVM_CAP_X86_ROBUST_SINGLESTEP:
		r = 1;
		break;
	case KVM_CAP_COALESCED_MMIO:
		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
		break;
	case KVM_CAP_VAPIC:
		r = !kvm_x86_ops->cpu_has_accelerated_tpr();
		break;
	case KVM_CAP_NR_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
	case KVM_CAP_NR_MEMSLOTS:
		r = KVM_MEMORY_SLOTS;
		break;
	case KVM_CAP_PV_MMU:	/* obsolete */
		r = 0;
		break;
	case KVM_CAP_IOMMU:
		r = iommu_found();
		break;
	case KVM_CAP_MCE:
		r = KVM_MAX_MCE_BANKS;
		break;
	default:
		r = 0;
		break;
	}
	return r;

}

long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	long r;

	switch (ioctl) {
	case KVM_GET_MSR_INDEX_LIST: {
		struct kvm_msr_list __user *user_msr_list = argp;
		struct kvm_msr_list msr_list;
		unsigned n;

		r = -EFAULT;
		if (copy_from_user(&msr_list, user_msr_list, sizeof msr_list))
			goto out;
		n = msr_list.nmsrs;
		msr_list.nmsrs = num_msrs_to_save + ARRAY_SIZE(emulated_msrs);
		if (copy_to_user(user_msr_list, &msr_list, sizeof msr_list))
			goto out;
		r = -E2BIG;
		if (n < msr_list.nmsrs)
			goto out;
		r = -EFAULT;
		if (copy_to_user(user_msr_list->indices, &msrs_to_save,
				 num_msrs_to_save * sizeof(u32)))
			goto out;
		if (copy_to_user(user_msr_list->indices + num_msrs_to_save,
				 &emulated_msrs,
				 ARRAY_SIZE(emulated_msrs) * sizeof(u32)))
			goto out;
		r = 0;
		break;
	}
	case KVM_GET_SUPPORTED_CPUID: {
		struct kvm_cpuid2 __user *cpuid_arg = argp;
		struct kvm_cpuid2 cpuid;

		r = -EFAULT;
		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
			goto out;
		r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
						      cpuid_arg->entries);
		if (r)
			goto out;

		r = -EFAULT;
		if (copy_to_user(cpuid_arg, &cpuid, sizeof cpuid))
			goto out;
		r = 0;
		break;
	}
	case KVM_X86_GET_MCE_CAP_SUPPORTED: {
		u64 mce_cap;

		mce_cap = KVM_MCE_CAP_SUPPORTED;
		r = -EFAULT;
		if (copy_to_user(argp, &mce_cap, sizeof mce_cap))
			goto out;
		r = 0;
		break;
	}
	default:
		r = -EINVAL;
	}
out:
	return r;
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	kvm_x86_ops->vcpu_load(vcpu, cpu);
	if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) {
		unsigned long khz = cpufreq_quick_get(cpu);
		if (!khz)
			khz = tsc_khz;
		per_cpu(cpu_tsc_khz, cpu) = khz;
	}
	kvm_request_guest_time_update(vcpu);
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
	kvm_put_guest_fpu(vcpu);
	kvm_x86_ops->vcpu_put(vcpu);
}

static int is_efer_nx(void)
{
	unsigned long long efer = 0;

	rdmsrl_safe(MSR_EFER, &efer);
	return efer & EFER_NX;
}

static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
{
	int i;
	struct kvm_cpuid_entry2 *e, *entry;

	entry = NULL;
	for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
		e = &vcpu->arch.cpuid_entries[i];
		if (e->function == 0x80000001) {
			entry = e;
			break;
		}
	}
	if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) {
		entry->edx &= ~(1 << 20);
		printk(KERN_INFO "kvm: guest NX capability removed\n");
	}
}

/* when an old userspace process fills a new kernel module */
static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
				    struct kvm_cpuid *cpuid,
				    struct kvm_cpuid_entry __user *entries)
{
	int r, i;
	struct kvm_cpuid_entry *cpuid_entries;

	r = -E2BIG;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		goto out;
	r = -ENOMEM;
	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
	if (!cpuid_entries)
		goto out;
	r = -EFAULT;
	if (copy_from_user(cpuid_entries, entries,
			   cpuid->nent * sizeof(struct kvm_cpuid_entry)))
		goto out_free;
	for (i = 0; i < cpuid->nent; i++) {
		vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
		vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
		vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx;
		vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx;
		vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx;
		vcpu->arch.cpuid_entries[i].index = 0;
		vcpu->arch.cpuid_entries[i].flags = 0;
		vcpu->arch.cpuid_entries[i].padding[0] = 0;
		vcpu->arch.cpuid_entries[i].padding[1] = 0;
		vcpu->arch.cpuid_entries[i].padding[2] = 0;
	}
	vcpu->arch.cpuid_nent = cpuid->nent;
	cpuid_fix_nx_cap(vcpu);
	r = 0;
	kvm_apic_set_version(vcpu);
	kvm_x86_ops->cpuid_update(vcpu);

out_free:
	vfree(cpuid_entries);
out:
	return r;
}

static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
				     struct kvm_cpuid2 *cpuid,
				     struct kvm_cpuid_entry2 __user *entries)
{
	int r;

	r = -E2BIG;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		goto out;
	r = -EFAULT;
	if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
			   cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
		goto out;
	vcpu->arch.cpuid_nent = cpuid->nent;
	kvm_apic_set_version(vcpu);
	kvm_x86_ops->cpuid_update(vcpu);
	return 0;

out:
	return r;
}

static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
				     struct kvm_cpuid2 *cpuid,
				     struct kvm_cpuid_entry2 __user *entries)
{
	int r;

	r = -E2BIG;
	if (cpuid->nent < vcpu->arch.cpuid_nent)
		goto out;
	r = -EFAULT;
	if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
			 vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
		goto out;
	return 0;

out:
	cpuid->nent = vcpu->arch.cpuid_nent;
	return r;
}

static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
			   u32 index)
{
	entry->function = function;
	entry->index = index;
	cpuid_count(entry->function, entry->index,
		    &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
	entry->flags = 0;
}

#define F(x) bit(X86_FEATURE_##x)

static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
			 u32 index, int *nent, int maxnent)
{
	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
#ifdef CONFIG_X86_64
	unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
				? F(GBPAGES) : 0;
	unsigned f_lm = F(LM);
#else
	unsigned f_gbpages = 0;
	unsigned f_lm = 0;
#endif
	unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;

	/* cpuid 1.edx */
	const u32 kvm_supported_word0_x86_features =
		F(FPU) | F(VME) | F(DE) | F(PSE) |
		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
		F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
		0 /* Reserved, DS, ACPI */ | F(MMX) |
		F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
		0 /* HTT, TM, Reserved, PBE */;
	/* cpuid 0x80000001.edx */
	const u32 kvm_supported_word1_x86_features =
		F(FPU) | F(VME) | F(DE) | F(PSE) |
		F(TSC) | F(MSR) | F(PAE) | F(MCE) |
		F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
		F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
		F(PAT) | F(PSE36) | 0 /* Reserved */ |
		f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
		F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp |
		0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
	/* cpuid 1.ecx */
	const u32 kvm_supported_word4_x86_features =
		F(XMM3) | 0 /* Reserved, DTES64, MONITOR */ |
		0 /* DS-CPL, VMX, SMX, EST */ |
		0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
		0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
		0 /* Reserved, DCA */ | F(XMM4_1) |
		F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
		0 /* Reserved, XSAVE, OSXSAVE */;
	/* cpuid 0x80000001.ecx */
	const u32 kvm_supported_word6_x86_features =
		F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ |
		F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
		F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(SSE5) |
		0 /* SKINIT */ | 0 /* WDT */;

	/* all calls to cpuid_count() should be made on the same cpu */
	get_cpu();
	do_cpuid_1_ent(entry, function, index);
	++*nent;

	switch (function) {
	case 0:
		entry->eax = min(entry->eax, (u32)0xb);
		break;
	case 1:
		entry->edx &= kvm_supported_word0_x86_features;
		entry->ecx &= kvm_supported_word4_x86_features;
		/* we support x2apic emulation even if host does not support
		 * it since we emulate x2apic in software */
		entry->ecx |= F(X2APIC);
		break;
	/* function 2 entries are STATEFUL. That is, repeated cpuid commands
	 * may return different values. This forces us to get_cpu() before
	 * issuing the first command, and also to emulate this annoying behavior
	 * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */
	case 2: {
		int t, times = entry->eax & 0xff;

		entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
		entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
		for (t = 1; t < times && *nent < maxnent; ++t) {
			do_cpuid_1_ent(&entry[t], function, 0);
			entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
			++*nent;
		}
		break;
	}
	/* function 4 and 0xb have additional index. */
	case 4: {
		int i, cache_type;

		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		/* read more entries until cache_type is zero */
		for (i = 1; *nent < maxnent; ++i) {
			cache_type = entry[i - 1].eax & 0x1f;
			if (!cache_type)
				break;
			do_cpuid_1_ent(&entry[i], function, i);
			entry[i].flags |=
			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
			++*nent;
		}
		break;
	}
	case 0xb: {
		int i, level_type;

		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
		/* read more entries until level_type is zero */
		for (i = 1; *nent < maxnent; ++i) {
			level_type = entry[i - 1].ecx & 0xff00;
			if (!level_type)
				break;
			do_cpuid_1_ent(&entry[i], function, i);
			entry[i].flags |=
			       KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
			++*nent;
		}
		break;
	}
	case 0x80000000:
		entry->eax = min(entry->eax, 0x8000001a);
		break;
	case 0x80000001:
		entry->edx &= kvm_supported_word1_x86_features;
		entry->ecx &= kvm_supported_word6_x86_features;
		break;
	}

	kvm_x86_ops->set_supported_cpuid(function, entry);

	put_cpu();
}

#undef F

static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
				     struct kvm_cpuid_entry2 __user *entries)
{
	struct kvm_cpuid_entry2 *cpuid_entries;
	int limit, nent = 0, r = -E2BIG;
	u32 func;

	if (cpuid->nent < 1)
		goto out;
	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
		cpuid->nent = KVM_MAX_CPUID_ENTRIES;
	r = -ENOMEM;
	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
	if (!cpuid_entries)
		goto out;